I'm flying from San Francisco on United and the agent asks
What city are you departing from?, this question would be redundant and create a poor user experience.
Instead, slot fillers ensure that only missing information is requested.
Key benefits
- Collecting and remembering information. With slot fillers, all required data is gathered and retained throughout the conversation, reducing errors and making conversations with the agent smoother and more natural.
- Handling different input types. Slot fillers accept various formats, for example, dates and numbers, making them flexible for user inputs.
Restrictions
- Slot fillers fail when multiple values share the same slot type, making it impossible to distinguish between them. For example, in
I'm flying from SFO to ORD on United, the agent can’t distinguish between the departure airport and the arrival airport because both matchairport_code. To avoid this restriction, you can:- Create separate slot fillers for each value:
Departure Airport: use a context key, for example,departure_city.Arrival Airport: use a context key, for example,arrival_city.
- Modify the flow to ask distinct questions for each slot instead of extracting both from a single user input.
- Create separate slot fillers for each value:
Work with slot fillers
- GUI
- API
You can create, edit, and delete slot fillers in Advanced > NLU > Slot Fillers.
Slot filler settings
Required fields
Required fields
Optional fields
Optional fields
The following parameters are in the Advanced section.
Example
Step 1. add slot fillers
Step 1. add slot fillers
- Create a new flow called
Slot Fillers. - Go to Advanced > NLU and attach relevant lexicons, for example,
airportsandairlines. - On the Slot Fillers tab, follow these steps:
- Create a new slot filler named
Airline. - Select Slot from the Type list.
- Enter
airlinein the Slot Name field. In the Advanced section, activate Store result in Context and enterairlinein the Context Key field.
- Create a new slot filler named
- Repeat steps 3.1 through 3.3 to create another slot filler named
Airport, then enterairport_codein the Slot Name and Context Key fields. - Click Build Model.
Step 2. configure question nodes
Step 2. configure question nodes
- Create a Question node, enter
What is your departure airport?in the Text field, and select Slot from the Question Type list. - Enter
airport_codein the Slot Name and Context Key to use fields. - Activate Skip if Answer exists in Context.
- Repeat the process for
What is your airline?, then enterairlinein the Slot Name and Context Key to use fields.
Step 3. test slot fillers
Step 3. test slot fillers
Provide all information at once:
User input:
Result: No additional questions are asked.
Provide partial information:
User input:
Agent:
User input:
Result: The agent skips asking for the airline.
User input:
I'm leaving San Francisco on United.Result: No additional questions are asked.
Provide partial information:
User input:
I'm flying on United.Agent:
What is your departure airport?User input:
SFOResult: The agent skips asking for the airline.